Facial Expression Recognition based on Image Gradient and Deep Convolutional Neural Network

Facial expression recognition (FER), which is one of the basic ways of interacting with machines, has attracted much attention in the recent years. In this paper, a novel FER system based on a deep convolutional neural network (DCNN) is presented. Motivated by the powerful ability of DCNN in order to learn the features and image classification, the goal of this research work is to design a compatible and discriminative input for pre-trained AlexNet-DCNN. The proposed method consists of 4 steps. First, extracting three channels of the image including the original gray-level image in addition to the horizontal and vertical gradients of the image similar to the red, green, and blue color channels of an RGB image as the DCNN input. Secondly, data augmentation including scale, rotation, width shift, height shift, zoom, horizontal flip, and vertical flip of the images are prepared in addition to the original images for training DCNN. Then the AlexNet-DCNN model is applied in order to learn the high-level features corresponding to different emotion classes. Finally, transfer learning is implemented on the proposed model, and the presented model is fine-tuned on the target datasets. The average recognition accuracies of 92.41% and 93.66% are achieved for the JAFFE and CK+ datasets, respectively. The experimental results on two benchmark emotional datasets show a promising performance of the proposed model that can improve the performance of the current FER systems.